CivArchive
    Olga Kurylenko (JG) - v2.0
    NSFW
    Preview undefined
    Preview undefined
    Preview undefined
    Preview undefined
    Preview undefined
    Preview undefined
    Preview undefined
    Preview undefined
    Preview undefined
    Preview undefined

    Olga Kurylenko is a Ukranian/French actress and model, known for many roles in films such as Hitman or Quantum of Solace.

    Note: This TI has been updated. Please refer to the "About this version" section for more info on the training process and settings.

    Since I'm on vacation, I've started training TIs on a free colab shared by @Scottymac (who was also kind enough to provide a step-by-step tutorial on how to use it--thanks a bunch, mate!). It allows me to do a full batch size (even without paying Colab Pro, I can run the training process with a batch size of 6 and gradient 3).

    This is kind of an experiment for me too, as I've trained the model without captions for the first time. And I'd say the results are surprisingly good, but I'll need to further test the process to get a clearer idea about its pros and cons.

    I've tested a few steps: 120, 180 and 500. Probably should have tested more, but I liked the results with step 500 so much that I thought it was unnecessary. Training rate, as usual, was a fixed 0.004.

    Appreciate my work? My TIs are free, but you can always buy me a coffee. :)

    Curious about my (usual) work process? I have summarized it here.

    How to create a good prompt using my TIs

    You're obviously free to experiment, but bear in mind that my TIs are trained with a more or less fixed phrasing, that normally starts with:

    "photo of EMBEDDING_NAME, a woman"

    So I recommend always starting your prompt like that and then building the rest of the prompt from there. For instance, "photo of beautiful (0lg4kury:0.99), a woman as a movie star, hair upsweep updo, sweater off-shoulders, trousers, at a movie premiere gala, dark moody ambience (masterpiece:1.2) (photorealistic:1.2) (bokeh) (best quality) (detailed skin:1.2) (intricate details) (nighttime) (8k) (HDR) (cinematic lighting) (sharp focus), (looking at the camera:1.1), (closeup portrait:1.1)"

    Description

    Dataset images: 18

    Vectors: 2

    Learn rate: 0.004 (fixed)

    Batch size: 3

    Gradient: 2

    Steps: 1020

    FAQ

    TextualInversion
    SD 1.5

    Details

    Downloads
    2,243
    Platform
    CivitAI
    Platform Status
    Deleted
    Created
    6/25/2023
    Updated
    7/7/2025
    Deleted
    5/23/2025
    Trigger Words:
    okuryl3nko

    Files

    okuryl3nko.pt

    Mirrors

    CivitAI (1 mirrors)

    Available On (1 platform)

    Same model published on other platforms. May have additional downloads or version variants.